Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Host repository for the "Reproducible Deep Learning" PhD course
| Date | Stars |
|---|---|
| 2026-07-31 | 407 |
| 2026-08-02 | 407 |
| 2026-08-06 | 407 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Reproducible Deep Learning ## PhD Course in Data Science, 2021, 3 CFU [[Official website](https://www.sscardapane.it/teaching/reproducibledl/)] This practical PhD course explores the design of a simple *reproducible* environment for a deep learning project, using free, open-source tools ([Git](https://git-scm.com/), [DVC](http://dvc.org/), [Docker](https://www.docker.com/), [Hydra](https://github.com/facebookresearch/hydra), ...). The choice of tools is opinionated, and was made as a trade-off between practicality and didactical concerns. ## Local set-up The use case of the course is an audio classification model trained on the [ESC-50](https://github.com/karolpiczak/ESC-50) dataset. To set-up your local machine (or a proper virtual / remote environment), configure [Anaconda](https://www.anaconda.com/products/individual), and create a clean environment: ```bash conda create -n reprodl; conda activate reprodl ``` > ⚠️ For an alternative setup without Anaconda, see [issue #2](https://github.com/sscardapane/reprodl2021/issues/2). Then, install a few generic prerequisites (notebook handling, Pandas, …): ```bash conda install -y -c conda-forge notebook matplotlib pandas ipywidgets pathlib ``` Finally, install [PyTorch](https://pytorch.org/) and [PyTorch Lightning](https://github.com/PyTorchLightning/pytorch-lightning). The instructions below can vary depending on whether you have a CUDA-enabled machine, Linux, etc. In general, follow the instructions from the websites. ```bash conda install -y pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch -c conda-forge conda install -y pytorch-lightning -c conda-forge ``` This should be enough to let you run the [initial notebook](https://github.com/sscardapane/reprodl2021/blob/main/Initial%20Notebook.ipynb). More information on the use case can be found inside the notebook itself. > :warning: For Windows only, install a [backend for torchaudio](https://pytorch.org/audio/stable/backend.html): > ```bash > pip install soundfile > ``` ### Additional set-up steps The following steps are not mandatory, but will considerably simplify the experience. 1. If you are on Windows, install the [Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/install-win10). This is useful in a number of contexts, including Docker installation. 2. We will use Git from the command line multiple times, so consider enabling [GitHub access with an SSH key](https://docs.github.com/en/github/authenticating-to-github/connecting-to-github-with-ssh). 3. We will experiment with Docker reproducibility on the [Sapienza DGX environment](https://www.uniroma1.it/sites/default/files/field_file_allegati/presentazione_ga_13-05-2019_sgiagu.pdf). If you have not done so already, set-up your access to the machine. ## Organization of the course <p align="center"> <img align="center" src="https://github.com/sscardapane/reprodl2021/blob/main/reprodl_overview.png" width="500" style="border: 1px solid black;"> </p> The course is split into **exercises** (e.g., adding DVC support). The material for each exercise is provided as a Git branch. To follow an exercise, switch to the corresponding branch, and follow the README there. If you want to see the completed exercise, add *_completed* to the name of the branch. Additional material and information can be found on the [main website](https://www.sscardapane.it/teaching/reproducibledl/) of the course. **List of exercises**: - [x] Experimenting with Git, branches, and scripting (*exercise1_git*). - [x] Adding Hydra configuration (*exercise2_hydra*). - [x] Versioning data with DVC (*exercise3_dvc*). - [x] Creating a Dockerfile (*exercise4_docker*). - [x] Experiment management with Weight & Biases (*exercise5_wandb*). - [x] Unit testing and formatting with continuous integration (*exercise6_hooks*). ### An example If you want to follow the first exercise, switch to the corresponding branch and follow the instructions from there: ```bash git checko
Excerpt of 7,960 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d9a01ab76c473519, desc:reproducible